用流模型统一生成导航策略，效率提升且跨平台零样本迁移
FLUX: Accelerating Cross-Embodiment Generative Navigation Policies via Rectified Flow and Static-to-Dynamic Learning
- 通过线性概率流替代迭代去噪，实现高效直行轨迹生成
- 在六类任务中达最优表现，静态到动态训练提升鲁棒性
- 适合需要高效、通用导航的机器人研发与仿真测试
自主导航需涵盖从静态目标到达至动态社交穿越在内的多种能力，但评估标准分散。我们提出 DynBench 动态导航基准，包含物理上合理的群体模拟，结合现有静态协议，支持对六种基础导航任务的全面评估。在此框架下，我们提出 FLUX，首个基于流的统一导航策略。通过线性化概率流，FLUX 以直线轨迹替代迭代去噪，相比先前流方法提升每步推理效率 47%，相比扩散方法提升 29%。采用从静态到动态的课程学习，FLUX 先建立几何先验，再在动态社交环境中通过强化学习优化。该机制不仅增强社交感知能力，还通过随机动作分布捕捉恢复行为，提升静态任务鲁棒性。FLUX 在所有任务中达到最先进水平，并在轮式、四足和人形平台实现无需微调的零样本仿真到现实迁移。
原文摘要 · Abstract (English)
Autonomous navigation requires a broad spectrum of skills, from static goal-reaching to dynamic social traversal, yet evaluation remains fragmented across disparate protocols. We introduce DynBench, a dynamic navigation benchmark featuring physically valid crowd simulation. Combined with existing static protocols, it supports comprehensive evaluation across six fundamental navigation tasks. Within this framework, we propose FLUX, the first flow-based unified navigation policy. By linearizing probability flow, FLUX replaces iterative denoising with straight-line trajectories, improving per-step inference efficiency by 47% over prior flow-based methods and 29% over diffusion-based ones. Following a static-to-dynamic curriculum, FLUX initially establishes geometric priors and is subsequently refined through reinforcement learning in dynamic social environments. This regime not only strengthens socially-aware navigation but also enhances static task robustness by capturing recovery behaviors through stochastic action distributions. FLUX achieves state-of-the-art performance across all tasks and demonstrates zero-shot sim-to-real transfer on wheeled, quadrupedal, and humanoid platforms without any fine-tuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。